Update app.py

app.py

@@ -75,7 +75,7 @@ def retrieved_info(query, rag_model = rag_model, generating_model = model):
     # Generating answer using gemma model
     tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
     input_ids = tokenizer(generation_model_input, return_tensors='pt').to(device)
-    output = generating_model.generate(input_ids, max_new_tokens = 512)
+    output = generating_model.generate(input_ids, max_new_tokens = 256)
     
     return tokenizer.decode(output[0])
 
@@ -116,7 +116,7 @@ demo = gr.ChatInterface(
     type = 'messages',
     additional_inputs=[
         gr.Textbox(value="You are a helpful and friendly assistant.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=2048, value=256, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
             minimum=0.1,